Fair Graph Neural Network with Supervised Contrastive Regularization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917634952396800 |
|---|---|
| author | Kejani, Mahdi Tavassoli Dornaika, Fadi Loubes, Jean-Michel |
| author_facet | Kejani, Mahdi Tavassoli Dornaika, Fadi Loubes, Jean-Michel |
| contents | In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation. However, challenges arise from biases that can be hidden not only in the node attributes but also in the connections between entities. Therefore, ensuring fairness in graph neural network learning has become a critical problem. To address this issue, we propose a novel model for training fairness-aware GNN, which enhances the Counterfactual Augmented Fair Graph Neural Network Framework (CAF). Our approach integrates Supervised Contrastive Loss and Environmental Loss to enhance both accuracy and fairness. Experimental validation on three real datasets demonstrates the superiority of our proposed model over CAF and several other existing graph-based learning methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06090 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fair Graph Neural Network with Supervised Contrastive Regularization Kejani, Mahdi Tavassoli Dornaika, Fadi Loubes, Jean-Michel Machine Learning Artificial Intelligence In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation. However, challenges arise from biases that can be hidden not only in the node attributes but also in the connections between entities. Therefore, ensuring fairness in graph neural network learning has become a critical problem. To address this issue, we propose a novel model for training fairness-aware GNN, which enhances the Counterfactual Augmented Fair Graph Neural Network Framework (CAF). Our approach integrates Supervised Contrastive Loss and Environmental Loss to enhance both accuracy and fairness. Experimental validation on three real datasets demonstrates the superiority of our proposed model over CAF and several other existing graph-based learning methods. |
| title | Fair Graph Neural Network with Supervised Contrastive Regularization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.06090 |